Reward-Guided Individualised Communication for Deep Reinforcement Learning in Multi-Agent Systems.

Yi-Yu Lin Xiao-Jun Zeng

Published in: UKCI (2023)

Keyphrases

learning in multi agent systems
reinforcement learning
learning agents
cooperative
multi agent learning
multiagent systems
function approximation
multi agent
multi agent systems
state space
optimal policy
reinforcement learning algorithms
domain knowledge
inductive learning
reward function
learning agent